cold-outbound-sequencer
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data, such as CSV files, email platform exports, and pasted prospect lists. However, it explicitly includes defensive instructions requiring the agent to treat all such data as untrusted and forbidding the execution of any instructions found within those files.
- [DATA_EXPOSURE]: The skill handles business-sensitive data (ICP, list sources, and email metrics) but stores output in standard local memory paths for the agent's workflow without external exfiltration patterns.
- [SAFE]: The skill follows security best practices by clearly labeling compliance information as operational guidance rather than legal advice, and it restricts its scope to design rather than the adjudication of sensitive consent records.
Audit Metadata